⚡ Bolt: Implement 8-bit dynamic quantization for LLM sentiment analysis

[hombredennis66]

💡 What: Added torch.quantization.quantize_dynamic to the linear layers of the DistilBERT sentiment analysis pipeline in llm_service.py.

🎯 Why: Model inference on CPU is a significant bottleneck. 8-bit dynamic quantization is a low-risk, high-impact optimization that specifically targets linear layers in Transformer models for faster CPU execution.

📊 Impact:

• Latency Reduction: ~48% improvement (from ~90.5ms to ~46.7ms per uncached request).
• Efficiency: Lower memory usage and CPU cycles per inference.

🔬 Measurement: Verified using a local benchmark script comparing average latency over 20 iterations after model warm-up. Functional integrity confirmed by running pytest test_main.py.

Note: Logged this optimization in .jules/bolt.md for future reference.

---

PR created automatically by Jules for task 8401813795655158213 started by @hombredennis66

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.